UPD: qemu-kvm 0.12.5 virtio-net page allocation error

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Am 03.10.2010 um 01:48 schrieb Peter Lieven:

> Hi,
> 
> running 0.12.5 with a Ubuntu LTS 10.04.1 64-bit kernel I see the following error after a few days with severe load (constant 100-200mbps input).
> 
> # uname -a
> Linux ubuntu-newsfeed 2.6.32-24-server #43-Ubuntu SMP Thu Sep 16 16:05:42 UTC 2010 x86_64 GNU/Linux

Linux newsfeed-spool 2.6.27.48-0.2-default seems not affected. I have a machine with even higher load (about 300-400mbits constant
network load) up for 4 months without a crash.

> 
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] swapper: page allocation failure. order:0, mode:0x20
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Pid: 0, comm: swapper Not tainted 2.6.32-24-server #43-Ub
> untu
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Call Trace:
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  <IRQ>  [<ffffffff810fa7ae>] __alloc_pages_slowpath+0x56e
> /0x580
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff810fa931>] __alloc_pages_nodemask+0x171/0x180
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8112d817>] alloc_pages_current+0x87/0xd0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff813db792>] try_fill_recv+0x182/0x200
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff813db9bd>] virtnet_poll+0x10d/0x160
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff81473c5f>] net_rx_action+0x10f/0x250
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8106e317>] __do_softirq+0xb7/0x1e0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff810c4dc0>] ? handle_IRQ_event+0x60/0x170
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff810142ec>] call_softirq+0x1c/0x30
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff81015cb5>] do_softirq+0x65/0xa0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8106e1b5>] irq_exit+0x85/0x90
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8155fd25>] do_IRQ+0x75/0xf0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff81013b13>] ret_from_intr+0x0/0x11
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  <EOI>  [<ffffffff81038acb>] ? native_safe_halt+0xb/0x10
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8101b69d>] ? default_idle+0x3d/0x90
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff81011e63>] ? cpu_idle+0xb3/0x110
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8154285b>] ? rest_init+0x6b/0x80
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8187edcc>] ? start_kernel+0x368/0x371
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8187e33a>] ? x86_64_start_reservations+0x125/0x129
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  [<ffffffff8187e438>] ? x86_64_start_kernel+0xfa/0x109
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Mem-Info:
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 DMA per-cpu:
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    0: hi:    0, btch:   1 usd:   0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    1: hi:    0, btch:   1 usd:   0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    2: hi:    0, btch:   1 usd:   0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    3: hi:    0, btch:   1 usd:   0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 DMA32 per-cpu:
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    0: hi:  186, btch:  31 usd:  59
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    1: hi:  186, btch:  31 usd: 159
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    2: hi:  186, btch:  31 usd: 102
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    3: hi:  186, btch:  31 usd: 151
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 Normal per-cpu:
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    0: hi:  186, btch:  31 usd:  51
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    1: hi:  186, btch:  31 usd: 157
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    2: hi:  186, btch:  31 usd: 162
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] CPU    3: hi:  186, btch:  31 usd: 175
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] active_anon:1857 inactive_anon:1602 isolated_anon:0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  active_file:458063 inactive_file:467825 isolated_file:0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  unevictable:0 dirty:74195 writeback:18395 unstable:0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  free:5214 slab_reclaimable:50506 slab_unreclaimable:3256
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029]  mapped:4151 shmem:1592 pagetables:400 bounce:0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 DMA free:15896kB min:28kB low:32kB high:40kB active_anon:0kB inactive_anon:0kB active_fil
> e:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15336kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB s
> lab_reclaimable:0kB slab_unreclaimable:8kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? 
> yes
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] lowmem_reserve[]: 0 3512 4017 4017
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 DMA32 free:4652kB min:7076kB low:8844kB high:10612kB active_anon:3832kB inactive_anon:110
> 8kB active_file:1642896kB inactive_file:1680672kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:3596500kB mlocked:0kB dirty:262008kB wri
> teback:61820kB mapped:10184kB shmem:2812kB slab_reclaimable:170892kB slab_unreclaimable:4164kB kernel_stack:8kB pagetables:512kB unstable:0kB bounce:0kB
> writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] lowmem_reserve[]: 0 0 505 505
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 Normal free:308kB min:1016kB low:1268kB high:1524kB active_anon:3596kB inactive_anon:5300
> kB active_file:189356kB inactive_file:190628kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:517120kB mlocked:0kB dirty:34772kB writebac
> k:11760kB mapped:6420kB shmem:3556kB slab_reclaimable:31132kB slab_unreclaimable:8852kB kernel_stack:1160kB pagetables:1088kB unstable:0kB bounce:0kB wr
> iteback_tmp:0kB pages_scanned:0 all_unreclaimable? no
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] lowmem_reserve[]: 0 0 0 0
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 DMA: 2*4kB 4*8kB 5*16kB 3*32kB 3*64kB 1*128kB 2*256kB 1*512kB 2*1024kB 2*2048kB 2*4096kB 
> = 15896kB
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 DMA32: 607*4kB 72*8kB 0*16kB 1*32kB 0*64kB 1*128kB 3*256kB 1*512kB 0*1024kB 0*2048kB 0*40
> 96kB = 4444kB
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Node 0 Normal: 27*4kB 3*8kB 2*16kB 0*32kB 1*64kB 1*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*409
> 6kB = 356kB
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] 927861 total pagecache pages
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] 296 pages in swap cache
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Swap cache stats: add 797, delete 501, find 10963/10986
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Free swap  = 3905004kB
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] Total swap = 3906552kB
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] 1048576 pages RAM
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] 34105 pages reserved
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] 668525 pages shared
> Oct  2 10:09:35 ubuntu-newsfeed kernel: [248407.790029] 344067 pages non-shared
> 
> Is this anything known?
> 
> After this error, the network device hangs. However, it can be recovered by setting ip link down and up again.
> 
> BR,
> Peter

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux